INDEX

Explanations

legal terminology and concepts related to rights and obligations

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Negative Logits

 alimentaria

-0.48

 pubblico

-0.47

autique

-0.47

 piłkarz

-0.45

 doppio

-0.45

Brainz

-0.45

Splits

-0.45

JvmStatic

-0.45

RTEE

-0.45

 Архів

-0.44

POSITIVE LOGITS

 vague

0.81

 mysterious

0.66

 unstructured

0.65

luiting

0.65

 BoxFit

0.63

 general

0.61

providedIn

0.61

 miscellaneous

0.60

ImageContext

0.60

 unexplained

0.59

Activations Density 0.442%

legal terminology and concepts related to rights and obligations

No Known Activations